Skip to main content
Glama

ocr_text_vision

Extracts text from images using Apple Vision OCR, returning full text, per-line confidence scores, and bounding boxes. Use it for CJK and European language text recognition on macOS.

Instructions

Extract text from an image. Returns full text, per-line confidence, and bounding boxes.

Backend: vision. Apple Vision OCR — fast on-device GPU/ANE inference (macOS 10.15+). Best for CJK + major European languages. Zero install on macOS.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "ocr_text_vision"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo
modeNoaccurate
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.2
    • changedInput schema / properties / mode / default
      Previous value: -"base"New value: +"accurate"
  2. First observedv1.0.0

TDQS

B3.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does useful work: it discloses the return payload, on-device GPU/ANE inference (implying no network call), and an OS floor of macOS 10.15+. It stops short of stating that calls on non-macOS hosts will fail and says nothing about supported image formats or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Short and front-loaded, with the core action and return values in the first sentence and supporting context after. 'Backend: vision. Apple Vision OCR' is mildly redundant with the tool name, but the rest earns its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description does cover the return shape, which is a real strength. However, for a tool with three fully undocumented parameters and a platform restriction, the definition omits mode selection, language tag format, image-format constraints, and the behavior on unsupported hosts.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters, so the description must compensate and largely does not. The language hint loosely gestures at `lang` but gives no expected format, and `mode` (default 'accurate', presumably with a faster alternative) is never mentioned at all; `path` is only obliquely implied by 'from an image'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Extract text from an image') and enumerates the return shape (full text, per-line confidence, bounding boxes). The 'Backend: vision / Apple Vision OCR' line distinguishes it from siblings like ocr_text_paddle and ocr_text_xiaomi by naming the engine, though it never explicitly frames the choice as a comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Best for CJK + major European languages' and 'macOS 10.15+' imply when this tool is appropriate, and 'zero install' hints at a setup advantage. But there is no explicit when-not guidance and no sibling is named as the alternative for non-macOS hosts or for layout/table extraction despite eight closely related OCR siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.